--- license: apache-2.0 base_model: AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 tags: - openvino - int4 - intel-arc - qwen3_5 - mixture-of-experts - roleplay - uncensored language: - en --- # Ornith-1.0-35B (Qwen3.6-35B-A3B), OpenVINO INT4. 106 tok/s on ONE Intel Arc B70. This is AEON-7's Ornith "Ultimate Uncensored" tune of Qwen3.6-35B-A3B (256-expert MoE, 3B active parameters), converted to OpenVINO INT4 with Intel's own recipe. Sibling of my [tvall43 heretic conversion](https://huggingface.co/Wondernutts/tvall43-Qwen3.6-35B-A3B-heretic-int4-ov) of the same base model: same speed class, different tuning flavor. Runs on the stock 2026.2 runtime, no patches, coherent through 32K context. **One thing made this conversion special.** Ornith was saved by a bleeding-edge transformers (5.13-dev) that stores each of the 10,240 experts as separate tensors (30,720 tensor files worth of them), while every current export toolchain expects the fused layout and silently RANDOMIZES the experts if it does not find it. This conversion required re-fusing all 30,720 per-expert tensors back into the 80 fused ones, with the layout and packing order verified against the toolchain's own model skeleton before writing. If you are trying to convert any model saved in the new per-expert format, the fusion script and the full story are in the [toolkit repo](https://github.com/Wondernuttz/OpenVino-For-Gemma-4). But, you should know I did all that work to find out it was pretty tarded for roleplay, still good for workflow, but not the best at campfire stories. ## Measured performance (single Arc Pro B70, OpenVINO 2026.2) | Metric | Value | |---|---| | Decode, short context | ~106 tok/s | | Decode at 6K context | ~77 tok/s | | Prefill | pp512 ~1,100 tok/s; ~3,900 at 6K; 16K in ~7 s; 32K in ~22 s (curve measured on the [tvall43 twin](https://huggingface.co/Wondernutts/tvall43-Qwen3.6-35B-A3B-heretic-int4-ov), same architecture) | | Model load | ~16 s | | Weights | ~19 GB (needs a 24 GB+ card; B60/B70 class) | ## Long-context capability, verified by needle retrieval A password fact planted early in the prompt, retrieved at the end. Pass means the exact password. | Context | Result | |---|---| | 8K | PASS (2.5 s total) | | 16K | PASS (7.7 s) | | 24K | PASS (19.0 s) | | 32K | PASS (41.7 s, cold cache) | No rope patch, no precision workarounds, no special properties for single-stream use. The architecture is rated to 262K positions; 32K is as far as my test box's host RAM lets me verify. ## How to run Identical to the [tvall43 sibling](https://huggingface.co/Wondernutts/tvall43-Qwen3.6-35B-A3B-heretic-int4-ov): standard Qwen ` ` format, pre-closed ` \n\n ` block for fast no-think replies (remove it and give at least 1024 tokens to enable reasoning), and `{"DYNAMIC_QUANTIZATION_GROUP_SIZE": 0}` if you use continuous batching. Full runnable snippet on the sibling card; just point it at this folder. ```bash pip install openvino-genai==2026.2.0 huggingface_hub huggingface-cli download Wondernutts/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16-int4-ov --local-dir ./ornith-35b-ov ``` ## Provenance `Qwen/Qwen3.6-35B-A3B`, Ornith-1.0 "AEON Ultimate Uncensored" tune by [AEON-7](https://huggingface.co/AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16), per-expert-to-fused weight restoration and OpenVINO INT4 conversion (this repo). ## Intended use and content notice Uncensored general model, built and tested for roleplay and creative writing on local Intel hardware. The tune removes refusal behavior and outputs are unfiltered; you are responsible for lawful and appropriate use. Licensed under [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0), same as the upstream Qwen3.6 release.
